Skip to content
Agentmart
Submit a tool

analyze

需求分析阶段入口;聚合评分、追问与范围判定规则,按需加载 references/assets/scripts。

Skill by evidentloop

IndexedApache-2.0★ 368
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/evidentloop-analyze-b08985

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

需求分析阶段入口;聚合评分、追问与范围判定规则,按需加载 references/assets/scripts。

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/analyze

What's inside

Skill name
analyze
Description
需求分析阶段入口;聚合评分、追问与范围判定规则,按需加载 references/assets/scripts。
License
Apache-2.0
Instructions
49 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (5)

  • SKILL.md
  • question-output.md · assets/
  • success-output.md · assets/
  • analyze-rules.md · references/
  • score_requirement.py · scripts/

SKILL.md (first lines)

# Analyze(入口文档)

> 先读证据,再把目标、交付物和候选路径分开。

## 何时激活

- 进入需求分析阶段(`workflow` / `plan_only`)。
- 需要做需求评分、追问或复杂度路由判定。

## 执行骨架

1. 先加载 `references/analyze-rules.md`。
2. 读取用户提供的材料和相关代码,区分目标、交付物与候选路径,再做完整性评分。
3. 若评分不足,按 `auto_decide` 处理:
   - `false`:使用 `assets/question-output.md` 追问。
   - `true`:显式补充假设后继续。
4. 评分达标后,交接已确认的成功标准、范围、证据和仍会影响结果的未知项。
5. 输出阶段摘要,格式参考 `assets/success-output.md`。

## 资源导航

- 长规则:`references/analyze-rules.md`
- 共享写作规范:`../references/shared-writing-dna.md`(所有输出遵循)
- 输出契约:`../references/output-contract.md`(必需 section、条件增强、自检)
- 追问模板:`assets/question-output.md`
- 达标输出模板:`assets/success-output.md`
- 确定性评分脚本:`scripts/score_requirement.py`

## 确定性逻辑(脚本优先)

当需要可审计评分时,优先调用:

```bash
python3 skills/zh/skills/sopify/analyze/scripts/score_requirement.py \
  --goal-clarity 2 \
  --expected-outcome 2 \
  --scope-boundary 1 \
  --constraints 1 \
  --require-score 7
```

脚本输出 JSON,包含:总分、阈值判定、缺失维度清单。

## 边界

- 不在本技能直接生成方案包(交给 `design`)。
- 不在本技能直接执行代码修改(交给 `develop`)。

From evidentloop/sopify, Apache-2.0.

Signals

Stars
368
Forks
30
Open issues
0
Last commit (this folder)
Oct 20, 2026 (9 days ago)
Last release
Oct 21, 2026 (8 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from evidentloop

Cite this page

analyze skill. Agent Mart. https://agentmart.dev/skills/evidentloop-analyze-b08985 (last updated 2026-10-24)